html-erd-explorer

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for the agent to generate standalone HTML artifacts for database visualization based on user-provided schemas.
  • [SAFE]: The skill explicitly instructs the agent to follow security best practices to prevent XSS: 'Never set innerHTML from a string that includes a variable, user input, computed value, or imported data — it's an XSS vector'. It mandates using textContent and createElement instead.
  • [SAFE]: The skill enforces a minimal attack surface by requiring artifacts to be self-contained, forbidding the use of external runtimes, CDNs, or npm packages, with a limited exception for Google Fonts.
  • [SAFE]: No patterns of prompt injection, data exfiltration, obfuscation, or unauthorized command execution were detected. The skill's behavior is consistent with its stated purpose of schema documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 04:18 AM
Security Audit — agent-trust-hub — html-erd-explorer